Figures & data
Table 1. Comparison of CNNs-based models and transformer-based models.
Figure 8. (a) Input RGB image (b) Relative depth map predicted by Monodepth2 (c) Metric depth map predicted by MobileDepth.
![Figure 8. (a) Input RGB image (b) Relative depth map predicted by Monodepth2 (c) Metric depth map predicted by MobileDepth.](/cms/asset/fd0543ae-0a38-45cf-b550-ff5f748730b1/uaai_a_2364159_f0008_oc.jpg)
Table 2. Quantitative results. Compare our method to existing methods on KITTI.
Table 3. Quantitative results. Compare our method to existing methods on NYU.
Table 4. Comparison of MobileDepth with existing models in parameters.
Table 5. Complexity of models.
Table 6. Ablation study for components and loss function.
Figure 10. Quantitative ablation comparison experiments. (a) The input image. (b) The ground truth. (c) The predicted depth map using MSE loss function. (d)The predicted depth map via full model. (e) The predicted depth map without DSAB block. (f) The predicted depth map without MV2 block.
![Figure 10. Quantitative ablation comparison experiments. (a) The input image. (b) The ground truth. (c) The predicted depth map using MSE loss function. (d)The predicted depth map via full model. (e) The predicted depth map without DSAB block. (f) The predicted depth map without MV2 block.](/cms/asset/f8663c7f-eb85-4d60-80c8-402a0797c271/uaai_a_2364159_f0010_oc.jpg)